Demographics analysis 3 - HSCP and COVID
COVID Admissions - January 2020 to Febraury 2022
HSCP - 9-digit code for Health and Social Care Partnerships (2016) of residence
HB - 9-digit code for health board of treatment based on boundaries as at 1st April 2019
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(here)## Warning: package 'here' was built under R version 4.1.3## here() starts at C:/Users/mahri/OneDrive/CodeClan/rshiny_dashboard_project/Work In Progress/Demographicslibrary(readxl)## Warning: package 'readxl' was built under R version 4.1.3library(janitor)##
## Attaching package: 'janitor'## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(ggplot2)
library(lubridate)## Warning: package 'lubridate' was built under R version 4.1.3##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(stringr)Read In Data
covid_admissions_HSCP_agesex <- read_csv(here("../../raw_data/covid_data/hospital_admissions_hscp_agesex_20220302.csv"))## Rows: 91972 Columns: 11
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (7): HSCP, AgeGroup, AgeGroupQF, Sex, SexQF, AdmissionType, AdmissionTypeQF
## dbl (4): WeekEnding, NumberAdmissions, Average20182019, PercentVariation
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.covid_admissions_HSCP_simd <- read_csv(here("../../raw_data/covid_data/hospital_admissions_hscp_simd_20220302.csv"))## Rows: 45998 Columns: 8
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (3): HSCP, AdmissionType, AdmissionTypeQF
## dbl (5): WeekEnding, SIMDQuintile, NumberAdmissions, Average20182019, Percen...
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.Clean Names
covid_admissions_HSCP_agesex <- janitor::clean_names(covid_admissions_HSCP_agesex)
covid_admissions_HSCP_simd <- janitor::clean_names(covid_admissions_HSCP_simd)Change week_ending column to a date and creating new day, month, year AND a month and year col
#HSCP x age sex
covid_admissions_HSCP_agesex <- covid_admissions_HSCP_agesex %>%
mutate(week_ending = ymd(week_ending))
covid_admissions_HSCP_agesex <- covid_admissions_HSCP_agesex %>%
mutate(
wk_ending_day = day(week_ending),
wk_ending_month = month(week_ending, label = TRUE, abbr = FALSE),
wk_ending_year = year(week_ending)
) %>%
unite(wk_ending_yr_month,
wk_ending_month, wk_ending_year,
remove = FALSE,
sep = " ")
covid_admissions_HSCP_agesex#HSCP x simd
covid_admissions_HSCP_simd <- covid_admissions_HSCP_simd %>%
mutate(week_ending = ymd(week_ending))
covid_admissions_HSCP_simd <- covid_admissions_HSCP_simd %>%
mutate(
wk_ending_day = day(week_ending),
wk_ending_month = month(week_ending, label = TRUE, abbr = FALSE),
wk_ending_year = year(week_ending)
) %>%
unite(wk_ending_yr_month,
wk_ending_month, wk_ending_year,
remove = FALSE,
sep = " ")
covid_admissions_HSCP_simdWhat are we working with?
Looking to see if i can join data? Probably??? All the HSPC corresponding health board values are S08000015 - s08000032 https://www.opendata.nhs.scot/dataset/geography-codes-and-labels/resource/944765d7-d0d9-46a0-b377-abb3de51d08e
The HB data set is all S08000015 - s08000032
covid_admissions_HSCP_agesex %>%
distinct(hscp)We only need ACUTE patients:
admission_type has: All, Emergency and Planned * all and emergency always have similar figures compared with planned.
covid_admissions_HSCP_agesex%>%
group_by(admission_type) %>%
summarise(total = n())covid_admissions_HSCP_agesex %>%
group_by(age_group) %>%
summarise(total = n())covid_admissions_HSCP_simd%>%
group_by(admission_type) %>%
summarise(total = n())covid_admissions_HSCP_simd %>%
group_by(simd_quintile) %>%
summarise(total = n())- let’s remove “all” as we only want acute
covid_admissions_HSCP_agesex <- covid_admissions_HSCP_agesex %>%
filter(admission_type == "Emergency")
covid_admissions_HSCP_simd <- covid_admissions_HSCP_simd %>%
filter(admission_type == "Emergency")- We can remove simd NAs
- ANd we don’t need ALL ages either… edit: yes we do:
- The “sex” column “Male, Female, All” - m & f only come under “All ages”!
covid_admissions_HSCP_simd <- covid_admissions_HSCP_simd %>%
drop_na(simd_quintile)
covid_admissions_HSCP_AGE <- covid_admissions_HSCP_agesex %>%
filter(age_group != "All ages")HSCP - sex and age
HB - Age - Total Covid admissions
Firstly need a total column for each age group per month:
#Under 5
monthly_covid_ads_HSCP_under5 <- covid_admissions_HSCP_AGE %>%
filter(age_group == "Under 5") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
monthly_past_average_HSCP_under5 <- monthly_covid_ads_HSCP_under5 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
monthly_past_average_HSCP_under5#5 - 14
monthly_covid_ads_HSCP_5to14 <- covid_admissions_HSCP_AGE %>%
filter(age_group == "5 - 14") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
monthly_past_average_HSCP_5to14 <- monthly_covid_ads_HSCP_5to14 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
monthly_past_average_HSCP_5to14#15 - 44
monthly_covid_ads_HSCP_15to44 <- covid_admissions_HSCP_AGE %>%
filter(age_group == "15 - 44") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
monthly_past_average_HSCP_15to44 <- monthly_covid_ads_HSCP_15to44 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
monthly_past_average_HSCP_15to44# 45 - 64
a <- covid_admissions_HSCP_AGE %>%
filter(age_group == "45 - 64") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
a2 <- a %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
a2#65-74
b <- covid_admissions_HSCP_AGE %>%
filter(age_group == "65 - 74") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
b2 <- b %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
b2#75-84
c <- covid_admissions_HSCP_AGE %>%
filter(age_group == "75 - 84") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
c2 <- c %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
c2#85 and over
d <- covid_admissions_HSCP_AGE %>%
filter(age_group == "85 and over") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
d2 <- d %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
d2bind together so we have totals for each month:
covid_admissions_HSCP_age_totals <- bind_rows(monthly_past_average_HSCP_under5,
monthly_past_average_HSCP_5to14,
monthly_past_average_HSCP_15to44,
a2, b2, c2, d2)
covid_admissions_HSCP_age_totalsApril 2020 will be shown first and ages are a mess. So:
dates <- c("January 2020", "February 2020", "March 2020", "April 2020",
"May 2020", "June 2020", "July 2020", "August 2020",
"September 2020", "October 2020", "November 2020", "December 2020",
"January 2021", "February 2021", "March 2021", "April 2021",
"May 2021", "June 2021", "July 2021", "August 2021",
"September 2021", "October 2021", "November 2021", "December 2021",
"January 2022", "February 2022")
summer_dates <- c("April 2020", "May 2020", "June 2020", "July 2020",
"August 2020", "September 2020", "April 2021", "May 2021",
"June 2021", "July 2021", "August 2021", "September 2021")
winter_dates <- c("January 2020", "February 2020", "March 2020", "October 2020",
"November 2020", "December 2020", "January 2021",
"February 2021", "March 2021", "October 2021",
"November 2021", "December 2021", "January 2022",
"February 2022")
PLOT OF Total COVID admissions per month by age
group
covid_admissions_HSCP_age_totals %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month,
group = age_group,
colour = age_group)+
scale_x_discrete(limits = dates) +
geom_point()+
geom_line()+
labs(x = "Month and Year",
y = "Total admissions",
title = "HSCP Total admissions in COVID times per month by age group",
subtitle = "January, 2020 - February 2022",
colour = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
let’s try again to see if there’s difference in age groups and seasons: * Winter = Q4 and Q1 * Summer = Q2 and Q3
highlight_winter_HSCP_age <- covid_admissions_HSCP_age_totals %>%
filter(str_detect(wk_ending_yr_month,
"October|November|December|January|February|March"))
highlight_summer_HSCP_age <- covid_admissions_HSCP_age_totals %>%
filter(str_detect(wk_ending_yr_month,
"April|May|June|July|August|September"))Re-trying above graph - messy but can be looked into. * Total COVID admissions per month by age group
covid_admissions_HSCP_age_totals %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month,
group = age_group,
fill = age_group)+
scale_x_discrete(limits = dates) +
geom_col()+
facet_wrap(~age_group)+
labs(x = "Month",
y = "Total admissions",
title = "HSCP Total admissions in COVID times per month by age group",
subtitle = "January, 2020 - February 2022",
fill = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
THE ABOVE BUT WINTER vs SUMMER
- Total COVID admissions per month by age group
- SUMMER
highlight_summer_HSCP_age %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month,
group = age_group,
fill = age_group)+
scale_x_discrete(limits = summer_dates) +
geom_col()+
facet_wrap(~age_group)+
labs(x = "Month",
y = "Total admissions",
title = "Total admissions in COVID times per SUMMER month, by age group",
subtitle = "Summer Months:
April, 2020 - September 2020
and April, 2021 - September 2021",
fill = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
- Total COVID admissions per month by age group
- WINTER
highlight_winter_HSCP_age %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month,
group = age_group,
fill = age_group)+
scale_x_discrete(limits = winter_dates) +
geom_col()+
facet_wrap(~age_group)+
labs(x = "Month and Year",
y = "Total admissions",
title = "HSCP Total admissions in COVID times per WINTER month by age group",
subtitle = "Winter Months:
January, 2020 - March 2020;
October 2020 - March 2021;
October 2021 - February 2022",
fill = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
HSCP -Age- Weekly COVID admissions against the average admissions in 2018 & 19
- wow this is messy
covid_admissions_HSCP_age_totals %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
group_by(age_group) %>%
ggplot()+
aes(x = number_admissions,
y = average20182019,
colour = age_group)+
geom_point() +
labs(x = "Weekly number of admissions in COVID times",
y = "Average weekly admissions to hospital in 2018-2019",
title = "Weekly admissions in COVID TIMES per age group against the
equivalent average weekly admissions in previous years",
subtitle = "COVID: January, 2020 - February, 2022 /
Previous years: 2018 - 2019",
colour = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
The above again just looking to see if there are differences in age groups * Weekly COVID admissions per age group against the average weekly admissions in previous years (2018&19)
covid_admissions_HSCP_age_totals %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
group_by(age_group) %>%
ggplot()+
aes(x = number_admissions,
y = average20182019,
colour = age_group)+
geom_point() +
facet_wrap(~age_group) +
labs(x = "Weekly number of admissions in COVID times",
y = "Average weekly admissions to hospital in 2018-2019",
title = "Weekly admissions in COVID TIMES per age group against the
equivalent average weekly admissions in previous years",
subtitle = "COVID: January, 2020 - February, 2022 /
Previous years: 2018 - 2019",
colour = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
The above but by month instead of EVERY input
covid_admissions_HSCP_age_totals %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
group_by(age_group) %>%
ggplot()+
aes(x = total_admissions_per_month,
y = total_past_average_ads_per_month,
colour = age_group)+
geom_point() +
labs(x = "Monthly number of admissions in COVID times",
y = "Average monthly admissions to hospital in 2018-2019",
title = "Monthly admissions in COVID TIMES per age group against the
equivalent average monthly admissions in previous years",
subtitle = "COVID: January, 2020 - February, 2022 /
Previous years: 2018 - 2019",
colour = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
Facet by age group
covid_admissions_HSCP_age_totals %>%
mutate(age_group = fct_relevel(age_group,
"Under 5", "5 - 14", "15 - 44",
"45 - 64", "65 - 74", "75 - 84",
"85 and over")) %>%
group_by(age_group) %>%
ggplot()+
aes(x = total_admissions_per_month,
y = total_past_average_ads_per_month,
colour = age_group)+
geom_point() +
facet_wrap(~age_group) +
labs(x = "Monthly number of admissions in COVID times",
y = "Average monthly admissions to hospital in 2018-2019",
title = "Monthly admissions in COVID TIMES per age group against the
equivalent average monthly admissions in previous years",
subtitle = "COVID: January, 2020 - February, 2022 /
Previous years: 2018 - 2019",
colour = "Age Group") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
HSCP - Sex - Average Covid Admissions vs Average 2018 and 2019 admissions
remember that the agesex df has male, female, and all - male and female come under “All ages” but not specific age groups
Creating columns for monthly totals - admissions, and average past ads
FOR FEMALES (males below):
monthly_covid_ads_HSCP_agesex_female <- covid_admissions_HSCP_agesex %>%
filter(sex == "Female") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
monthly_past_average_HSCP_agesex_female <- monthly_covid_ads_HSCP_agesex_female %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
monthly_past_average_HSCP_agesex_female- Creating columns for monthly totals - admissions, and average past ads
- FOR MALES (females above):
# covid_admissions_HB_agesex %>%
# distinct(sex)
# view(covid_admissions_HB_agesex)
monthly_covid_ads_HSCP_agesex_male <- covid_admissions_HSCP_agesex %>%
filter(sex == "Male") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month = sum(number_admissions))
monthly_past_average_HSCP_agesex_male <- monthly_covid_ads_HSCP_agesex_male %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
monthly_past_average_HSCP_agesex_malebringing male and females with totals per month together:
covid_admissions_HSCP_sex_totals <- bind_rows(monthly_past_average_HSCP_agesex_female,
monthly_past_average_HSCP_agesex_male)
covid_admissions_HSCP_sex_totalsTotal admissions across HSCPs by gender for week ending (this doesn’t work):
covid_admissions_HSCP_sex_totals%>%
group_by(sex) %>%
ggplot()+
aes(x = total_admissions_per_month,
y = total_past_average_ads_per_month,
colour = sex)+
scale_x_discrete(limits = dates) +
geom_point()+
geom_line()+
labs(title = "I AM AWARE THIS IS AWFUL")+
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
Trying again - Total admissions across HSCPs by gender for week ending
covid_admissions_HSCP_sex_totals %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month,
fill = sex)+
scale_x_discrete(limits = dates) +
geom_col(position = "dodge")+
labs(x = "Month and Year",
y = "Total Admissions per Month",
title = "HSCP Total Admissions in COVID times per Month by Sex",
fill = "Sex")+
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
weekly
covid_admissions_HSCP_sex_totals %>%
group_by(sex) %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month,
colour = sex)+
scale_x_discrete(limits = dates) +
geom_point()+
geom_line()+ # where is the line?
labs(x = "Month and Year",
y = "Total Admissions",
title = "HSCP Monthly admissions in COVID times by sex",
subtitle = "COVID: January, 2020 - February, 2022 /
Previous years: 2018 - 2019",
colour = "Sex") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
HEALTH BOARD - SIMD
HSCP - SIMD - Total Admissions
covid_admissions_HSCP_simd %>%
group_by(wk_ending_yr_month, simd_quintile) %>%
ggplot()+
aes(x = number_admissions,
y = average20182019,
colour = simd_quintile)+
scale_x_discrete(limits = dates) +
geom_point()+
geom_line()+
labs(title = "I AM AWARE THIS IS AWFUL")+
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
So, creating monthly total columns for each level of simd:
simd1 <- covid_admissions_HSCP_simd %>%
filter(simd_quintile == "1") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month_simd = sum(number_admissions))
simd1 <- simd1 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
simd1#2
simd2 <- covid_admissions_HSCP_simd %>%
filter(simd_quintile == "2") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month_simd = sum(number_admissions))
simd2 <- simd2 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
simd2#3
simd3 <- covid_admissions_HSCP_simd %>%
filter(simd_quintile == "3") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month_simd = sum(number_admissions))
simd3 <- simd3 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
simd3#4
simd4 <- covid_admissions_HSCP_simd %>%
filter(simd_quintile == "4") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month_simd = sum(number_admissions))
simd4 <- simd4 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
simd4#5
simd5 <- covid_admissions_HSCP_simd %>%
filter(simd_quintile == "5") %>%
group_by(wk_ending_yr_month) %>%
mutate(total_admissions_per_month_simd = sum(number_admissions))
simd5 <- simd5 %>%
group_by(wk_ending_yr_month) %>%
mutate(total_past_average_ads_per_month = sum(average20182019))
simd5bind these together:
covid_admissions_HSCP_simd_totals <- bind_rows(simd1, simd2, simd3, simd4, simd5)
covid_admissions_HSCP_simd_totalsPLOT total admissions per simd per month
covid_admissions_HSCP_simd_totals %>%
mutate(simd_quintile = fct_relevel(as.character(simd_quintile,
"1", "2", "3", "4", "5"))) %>%
group_by(wk_ending_yr_month, simd_quintile) %>%
ggplot()+
aes(x = wk_ending_yr_month,
y = total_admissions_per_month_simd,
group = simd_quintile,
colour = simd_quintile)+
scale_x_discrete(limits = dates) +
geom_point()+
geom_line()+
labs(x = "Month and year",
y = "Total admissions",
title = "HSCP Total admissions in COVID times per month by SIMD Level",
subtitle = "January, 2020 - February 2022",
colour = "SIMD Level:
1 = Most Deprived
5 = Least Deprived") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))
SIMD - AVERAGE admissions 2018 and 2019 against COVID admissions
covid_admissions_HSCP_simd_totals %>%
mutate(simd_quintile = fct_relevel(as.character(simd_quintile,
"1", "2", "3", "4", "5"))) %>%
group_by(simd_quintile) %>%
ggplot()+
aes(x = total_admissions_per_month_simd,
y = total_past_average_ads_per_month,
colour = simd_quintile)+
geom_point()+
labs(x = "Monthly number of admissions",
y = "Average monthly admissions to hospital in 2018-2019",
title = "Monthly admissions in COVID Times per SIMD level against the
equivalent average monthly admissions in previous years",
subtitle = "COVID: January, 2020 - February, 2022 /
Previous years: 2018 - 2019",
colour = "SIMD Level:
1 = Most Deprived
5 = Least Deprived") +
theme_bw()+
theme(axis.text.x = element_text(angle = 45, hjust = 0.9))